Model save
Browse files- README.md +37 -37
- all_results.json +15 -15
- eval_results.json +12 -12
- model.safetensors +1 -1
- runs/Sep22_19-02-28_xe8545-a100-05/events.out.tfevents.1727038341.xe8545-a100-05.377977.1 +3 -0
- runs/Sep23_09-29-20_xe8545-a100-19/events.out.tfevents.1727077824.xe8545-a100-19.125277.0 +3 -0
- train_results.json +3 -3
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model was trained from scratch on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Rewards/chosen: -3.
|
22 |
-
- Rewards/rejected: -
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins: 0.
|
25 |
-
- Logps/rejected: -
|
26 |
-
- Logps/chosen: -
|
27 |
-
- Logits/rejected: -
|
28 |
-
- Logits/chosen: -13.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -62,34 +62,34 @@ The following hyperparameters were used during training:
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.0013 | 2.6178 | 2500 | 1.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
|
94 |
|
95 |
### Framework versions
|
|
|
17 |
|
18 |
This model was trained from scratch on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0609
|
21 |
+
- Rewards/chosen: -3.7969
|
22 |
+
- Rewards/rejected: -4.0
|
23 |
+
- Rewards/accuracies: 0.5
|
24 |
+
- Rewards/margins: 0.2148
|
25 |
+
- Logps/rejected: -692.0
|
26 |
+
- Logps/chosen: -700.0
|
27 |
+
- Logits/rejected: -12.9375
|
28 |
+
- Logits/chosen: -13.25
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 0.187 | 0.1047 | 100 | 0.6760 | -0.4492 | -0.5586 | 0.5469 | 0.1084 | -344.0 | -364.0 | -14.5625 | -14.6875 |
|
66 |
+
| 0.1162 | 0.2094 | 200 | 0.6879 | -0.7734 | -0.875 | 0.5410 | 0.1016 | -376.0 | -396.0 | -11.6875 | -12.0625 |
|
67 |
+
| 0.1436 | 0.3141 | 300 | 0.7670 | -1.6562 | -1.7969 | 0.4941 | 0.1377 | -468.0 | -484.0 | -13.875 | -14.0625 |
|
68 |
+
| 0.1461 | 0.4188 | 400 | 0.7442 | -1.0469 | -1.0625 | 0.5039 | 0.0201 | -394.0 | -422.0 | -16.5 | -16.625 |
|
69 |
+
| 0.1352 | 0.5236 | 500 | 0.8131 | -1.6406 | -1.7031 | 0.5020 | 0.0630 | -460.0 | -482.0 | -15.5625 | -15.6875 |
|
70 |
+
| 0.1507 | 0.6283 | 600 | 0.8542 | -1.625 | -1.6328 | 0.4766 | 0.0096 | -452.0 | -482.0 | -17.25 | -17.375 |
|
71 |
+
| 0.1278 | 0.7330 | 700 | 0.8274 | -1.7891 | -1.9453 | 0.4980 | 0.1592 | -484.0 | -496.0 | -14.8125 | -15.0 |
|
72 |
+
| 0.1303 | 0.8377 | 800 | 0.8349 | -1.7734 | -1.7969 | 0.5195 | 0.0272 | -468.0 | -496.0 | -16.5 | -16.5 |
|
73 |
+
| 0.1614 | 0.9424 | 900 | 0.8078 | -2.2969 | -2.5 | 0.5332 | 0.1992 | -540.0 | -548.0 | -16.375 | -16.375 |
|
74 |
+
| 0.0199 | 1.0471 | 1000 | 0.8233 | -2.2656 | -2.3906 | 0.4863 | 0.1279 | -528.0 | -544.0 | -15.4375 | -15.875 |
|
75 |
+
| 0.0348 | 1.1518 | 1100 | 0.8452 | -2.0469 | -2.1562 | 0.5039 | 0.1187 | -504.0 | -524.0 | -17.0 | -17.125 |
|
76 |
+
| 0.0186 | 1.2565 | 1200 | 0.8788 | -2.9219 | -3.0312 | 0.5098 | 0.1074 | -592.0 | -612.0 | -14.75 | -15.0625 |
|
77 |
+
| 0.0277 | 1.3613 | 1300 | 0.8304 | -2.7969 | -2.8906 | 0.5137 | 0.0928 | -576.0 | -600.0 | -14.25 | -14.5 |
|
78 |
+
| 0.0212 | 1.4660 | 1400 | 0.8990 | -2.7969 | -2.9062 | 0.5 | 0.1099 | -580.0 | -600.0 | -14.25 | -14.4375 |
|
79 |
+
| 0.0333 | 1.5707 | 1500 | 0.9111 | -3.2031 | -3.2969 | 0.5215 | 0.0981 | -620.0 | -640.0 | -12.1875 | -12.625 |
|
80 |
+
| 0.0163 | 1.6754 | 1600 | 0.9215 | -3.2188 | -3.3281 | 0.4941 | 0.1104 | -620.0 | -640.0 | -11.0625 | -11.5 |
|
81 |
+
| 0.0309 | 1.7801 | 1700 | 0.9203 | -2.6719 | -2.7344 | 0.5059 | 0.0635 | -560.0 | -584.0 | -13.5625 | -13.8125 |
|
82 |
+
| 0.0228 | 1.8848 | 1800 | 0.9032 | -2.8594 | -2.9531 | 0.4941 | 0.0972 | -584.0 | -604.0 | -13.3125 | -13.5625 |
|
83 |
+
| 0.0116 | 1.9895 | 1900 | 0.9123 | -3.0156 | -3.125 | 0.5 | 0.1187 | -600.0 | -620.0 | -13.375 | -13.625 |
|
84 |
+
| 0.0011 | 2.0942 | 2000 | 0.9715 | -3.2656 | -3.4531 | 0.4980 | 0.1865 | -636.0 | -644.0 | -13.0625 | -13.3125 |
|
85 |
+
| 0.0019 | 2.1990 | 2100 | 1.0378 | -3.6719 | -3.9062 | 0.5098 | 0.2393 | -680.0 | -684.0 | -12.5 | -12.8125 |
|
86 |
+
| 0.0011 | 2.3037 | 2200 | 1.0456 | -3.7188 | -3.9375 | 0.5020 | 0.2227 | -684.0 | -692.0 | -12.8125 | -13.125 |
|
87 |
+
| 0.0009 | 2.4084 | 2300 | 1.0567 | -3.75 | -3.9688 | 0.5020 | 0.2217 | -684.0 | -692.0 | -12.9375 | -13.25 |
|
88 |
+
| 0.0022 | 2.5131 | 2400 | 1.0450 | -3.7188 | -3.9062 | 0.4961 | 0.1953 | -680.0 | -692.0 | -13.0 | -13.3125 |
|
89 |
+
| 0.0013 | 2.6178 | 2500 | 1.0499 | -3.7656 | -3.9688 | 0.5020 | 0.2080 | -684.0 | -696.0 | -12.9375 | -13.25 |
|
90 |
+
| 0.0006 | 2.7225 | 2600 | 1.0572 | -3.7812 | -3.9844 | 0.4961 | 0.2100 | -688.0 | -696.0 | -12.9375 | -13.25 |
|
91 |
+
| 0.0007 | 2.8272 | 2700 | 1.0600 | -3.7969 | -4.0 | 0.5020 | 0.2168 | -692.0 | -700.0 | -12.9375 | -13.25 |
|
92 |
+
| 0.0012 | 2.9319 | 2800 | 1.0609 | -3.7969 | -4.0 | 0.5 | 0.2148 | -692.0 | -700.0 | -12.9375 | -13.25 |
|
93 |
|
94 |
|
95 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_logits/chosen":
|
4 |
-
"eval_logits/rejected":
|
5 |
-
"eval_logps/chosen": -
|
6 |
-
"eval_logps/rejected": -
|
7 |
-
"eval_loss":
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -
|
10 |
-
"eval_rewards/margins":
|
11 |
-
"eval_rewards/rejected": -
|
12 |
-
"eval_runtime": 46.
|
13 |
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 42.
|
15 |
-
"eval_steps_per_second": 0.
|
16 |
"total_flos": 0.0,
|
17 |
-
"train_loss": 0.
|
18 |
-
"train_runtime":
|
19 |
"train_samples": 61118,
|
20 |
-
"train_samples_per_second": 14.
|
21 |
"train_steps_per_second": 0.231
|
22 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -13.625,
|
4 |
+
"eval_logits/rejected": -13.375,
|
5 |
+
"eval_logps/chosen": -660.0,
|
6 |
+
"eval_logps/rejected": -652.0,
|
7 |
+
"eval_loss": 1.0084375143051147,
|
8 |
+
"eval_rewards/accuracies": 0.505859375,
|
9 |
+
"eval_rewards/chosen": -3.40625,
|
10 |
+
"eval_rewards/margins": 0.2373046875,
|
11 |
+
"eval_rewards/rejected": -3.640625,
|
12 |
+
"eval_runtime": 46.5887,
|
13 |
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 42.929,
|
15 |
+
"eval_steps_per_second": 0.687,
|
16 |
"total_flos": 0.0,
|
17 |
+
"train_loss": 0.06693936966889477,
|
18 |
+
"train_runtime": 12411.6425,
|
19 |
"train_samples": 61118,
|
20 |
+
"train_samples_per_second": 14.773,
|
21 |
"train_steps_per_second": 0.231
|
22 |
}
|
eval_results.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_logits/chosen":
|
4 |
-
"eval_logits/rejected":
|
5 |
-
"eval_logps/chosen": -
|
6 |
-
"eval_logps/rejected": -
|
7 |
-
"eval_loss":
|
8 |
-
"eval_rewards/accuracies": 0.
|
9 |
-
"eval_rewards/chosen": -
|
10 |
-
"eval_rewards/margins":
|
11 |
-
"eval_rewards/rejected": -
|
12 |
-
"eval_runtime": 46.
|
13 |
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 42.
|
15 |
-
"eval_steps_per_second": 0.
|
16 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -13.625,
|
4 |
+
"eval_logits/rejected": -13.375,
|
5 |
+
"eval_logps/chosen": -660.0,
|
6 |
+
"eval_logps/rejected": -652.0,
|
7 |
+
"eval_loss": 1.0084375143051147,
|
8 |
+
"eval_rewards/accuracies": 0.505859375,
|
9 |
+
"eval_rewards/chosen": -3.40625,
|
10 |
+
"eval_rewards/margins": 0.2373046875,
|
11 |
+
"eval_rewards/rejected": -3.640625,
|
12 |
+
"eval_runtime": 46.5887,
|
13 |
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 42.929,
|
15 |
+
"eval_steps_per_second": 0.687
|
16 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2159808696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f472dc235cbb99fe76b154b2b864d83175abc92d57d69563a5aa4f5e7bea6214
|
3 |
size 2159808696
|
runs/Sep22_19-02-28_xe8545-a100-05/events.out.tfevents.1727038341.xe8545-a100-05.377977.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:059026933da5b6cd95cff54c93e49df31128c89ee4b41c5b286f0c8704b1a669
|
3 |
+
size 828
|
runs/Sep23_09-29-20_xe8545-a100-19/events.out.tfevents.1727077824.xe8545-a100-19.125277.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10f03e0e65200a8134df76441ca1bc5144a35b0c920b61e2e046271d9516a1ee
|
3 |
+
size 225670
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 61118,
|
7 |
-
"train_samples_per_second": 14.
|
8 |
"train_steps_per_second": 0.231
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.06693936966889477,
|
5 |
+
"train_runtime": 12411.6425,
|
6 |
"train_samples": 61118,
|
7 |
+
"train_samples_per_second": 14.773,
|
8 |
"train_steps_per_second": 0.231
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:156761cf315d6ce3558f8972c65a5b48c487072ae380e7d648fbe34fd22bd126
|
3 |
size 7608
|